The Research archive provides access to all Research articles published in past issues of Communications of the ACM.
September 2021
From Communications of the ACM
Technical Perspective: The Importance of WINOGRANDE
"WINOGRANDE" explores new methods of dataset development and adversarial filtering, expressly designed to prevent AI systems from making claims of smashing through benchmarks without making real progress.
From Communications of the ACM
Technical Perspective: Does Your Experiment Smell?
"PlanAlyzer," by Emma Tosch et al., details PlanAlyzer software, the first tool to statically check the validity of online experiments.
From Communications of the ACM
PlanAlyzer: Assessing Threats to the Validity of Online Experiments
We present the first approach for checking the internal validity of online experiments statically, that is, from code alone.
From Communications of the ACM
WinoGrande: An Adversarial Winograd Schema Challenge at Scale
We introduce WinoGrande, a large-scale dataset of 44k problems, inspired by the original Winograd Schema Challenge, but adjusted to improve both the scale and the hardness of the dataset.